Battlefield Environment Design for Multi-agent Reinforcement Learning

被引：2

作者：

Do, Seungwon ^{[1
]}

Baek, Jaeuk ^{[1
]}

Jun, Sungwoo ^{[1
]}

Lee, Changeun ^{[1
]}

机构：

[1] ETRI, Intelligent Convergence Res Lab, Daejeon 34129, South Korea

来源：

2022 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING (IEEE BIGCOMP 2022) | 2022年

关键词：

Reinforcement learning; multi-agent reinforcement learning; environment; battlefield; PLATFORM;

D O I：

10.1109/BigComp54360.2022.00069

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In reinforcement learning, an agent interacts with an environment for learning its policy. Designing the environment is an important part of training the agent because the change of the environment can affect the agent's policy. In this paper, we introduce the new battlefield environment for multi-agent reinforcement learning. In our environment, two groups of agents compete for their contrasting goals with limited information. As a result, we define the map of the environment and design the state, action, reward, and transition of each agent.

引用

页码：318 / 319

页数：2

共 50 条

[21] Hierarchical multi-agent reinforcement learning
Ghavamzadeh, Mohammad
Mahadevan, Sridhar
Makar, Rajbala
AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS, 2006, 13 (02) : 197 - 229
[22] Multi-agent Exploration with Reinforcement Learning
Sygkounas, Alkis
Tsipianitis, Dimitris
Nikolakopoulos, George
Bechlioulis, Charalampos P.
2022 30TH MEDITERRANEAN CONFERENCE ON CONTROL AND AUTOMATION (MED), 2022, : 630 - 635
[23] Partitioning in multi-agent reinforcement learning
Sun, R
Peterson, T
FROM ANIMALS TO ANIMATS 6, 2000, : 325 - 332
[24] Testing Reinforcement Learning Explainability Methods in a Multi-Agent Cooperative Environment
Domenech i Vila, Marc
Gnatyshak, Dmitry
Tormos, Adrian
Alvarez-Napagao, Sergio
ARTIFICIAL INTELLIGENCE RESEARCH AND DEVELOPMENT, 2022, 356 : 355 - 364
[25] Quantifying the effects of environment and population diversity in multi-agent reinforcement learning
Kevin R. McKee
Joel Z. Leibo
Charlie Beattie
Richard Everett
Autonomous Agents and Multi-Agent Systems, 2022, 36
[26] The Dynamics of Multi-Agent Reinforcement Learning
Dickens, Luke
Broda, Krysia
Russo, Alessandra
ECAI 2010 - 19TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2010, 215 : 367 - 372
[27] Applying opponent and environment modelling in decentralised multi-agent reinforcement learning
Chernyavskiy, Alexander
Skrynnik, Alexey
Panov, Aleksandr
COGNITIVE SYSTEMS RESEARCH, 2025, 89
[28] Multi-Agent Reinforcement Learning for Edge Resource Management with Reconstructed Environment
Miao, Weiwei
Zeng, Zeng
Zhang, Mingxuan
Quan, Siping
Zhang, Zhen
Li, Shihao
Zhang, Li
Sun, Qi
19TH IEEE INTERNATIONAL SYMPOSIUM ON PARALLEL AND DISTRIBUTED PROCESSING WITH APPLICATIONS (ISPA/BDCLOUD/SOCIALCOM/SUSTAINCOM 2021), 2021, : 1729 - 1736
[29] Multi-agent reinforcement learning: A survey
Busoniu, Lucian
Babuska, Robert
De Schutter, Bart
2006 9TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION, VOLS 1- 5, 2006, : 1133 - +
[30] Learning adversarial policy in multiple scenes environment via multi-agent reinforcement learning
Li, Yang
Wang, Xinzhi
Wang, Wei
Zhang, Zhenyu
Wang, Jianshu
Luo, Xiangfeng
Xie, Shaorong
CONNECTION SCIENCE, 2021, 33 (03) : 407 - 426

← 1 2 3 4 5 →